© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68370
    Prev
    Next
    INDEX
    Explanations

    Lorenzo and Interceptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UCIÓN
    -2.55
    ཋ
    -2.45
     prata
    -2.38
    );
    -2.38
     anún
    -2.34
     italiens
    -2.31
    に
    -2.28
    cjach
    -2.25
     palio
    -2.23
     vogliamo
    -2.20
    POSITIVE LOGITS
    \
    2.81
    ↵
    2.55
    的那个
    2.31
     
    2.31
     Для
    2.19
    ’
    2.19
     erase
    2.11
    聿
    2.08
    ↵↵
    2.08
     две
    2.05
    Activations Density 0.003%

    No Known Activations